- 17 Jul, 2012 25 commits
-
-
Eric Dumazet authored
netem does an early orphaning of skbs. Doing so breaks TCP Small Queue or any mechanism relying on socket sk_wmem_alloc feedback. Ideally, we should perform this orphaning after the rate module and before the delay module, to mimic what happens on a real link : skb orphaning is indeed normally done at TX completion, before the transit on the link. +-------+ +--------+ +---------------+ +-----------------+ + Qdisc +---> Device +--> TX completion +--> links / hops +-> + + + xmit + + skb orphaning + + propagation + +-------+ +--------+ +---------------+ +-----------------+ < rate limiting > < delay, drops, reorders > If netem is used without delay feature (drops, reorders, rate limiting), then we should avoid early skb orphaning, to keep pressure on sockets as long as packets are still in qdisc queue. Ideally, netem should be refactored to implement delay module as the last stage. Current algorithm merges the two phases (rate limiting + delay) so its not correct. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Hagen Paul Pfeifer <hagen@jauu.net> Cc: Mark Gordon <msg@google.com> Cc: Andreas Terzis <aterzis@google.com> Cc: Yuchung Cheng <ycheng@google.com> Acked-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/net-nextDavid S. Miller authored
Jett Kirsher says: ==================== This series contains updates to e1000e and ixgbe. ... Alexander Duyck (5): ixgbe: Simplify logic for getting traffic class from user priority ixgbe: Cleanup unpacking code for DCB ixgbe: Populate the prio_tc_map in ixgbe_setup_tc ixgbe: Add function for obtaining FCoE TC based on FCoE user priority ixgbe: Merge FCoE set_num and cache_ring calls into RSS/DCB config ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
-
Eric Dumazet authored
skb_fill_rx_data() pulls 64 byte of data in skb->data Its too much for TCP (with no options) on IPv4, as total size of headers is 14 + 40 = 54 This means tcp stack and splice() are suboptimal, since tcp payload is in part in tcp->data, and in part in skb frag. Signed-off-by: Eric Dumazet <edumazet@google.com> Acked-by: Padmanabh Ratnakar <padmanabh.ratnakar@emulex.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Padmanabh Ratnakar authored
Signed-off-by: Padmanabh Ratnakar <padmanabh.ratnakar@emulex.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Padmanabh Ratnakar authored
Incorporated review comment from Eric Dumazet. Added description about different RSS hash types which adapter is capable of. Will add support for ETHTOOL_GRXFH and ETHTOOL_SRXFX as suggested by Ben Hutchings in a later patch. Signed-off-by: Padmanabh Ratnakar <padmanabh.ratnakar@emulex.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Thomas Graf authored
The hash size is doubled when it needs to grow and compared against hash_max. The >= comparison will limit the hash table size to half of what is expected i.e. the default 512 hash_max will not allow the hash table to grow larger than 256. Also print the hash table limit instead of the desirable size when the limit is reached. Signed-off-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Dan Carpenter authored
We dereferenced "mclist" after the kfree(). Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Dan Carpenter authored
This should be ">=" here instead of ">". MLX4_NET_TRANS_RULE_NUM is 6. We use "spec->id" as an array offset into the __rule_hw_sz[] and __sw_id_hw[] arrays which have 6 elements. Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Acked-by: Hadar Hen Zion <hadarh@mellanox.co.il> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Denis Ovsienko authored
Userspace implementations of network routing protocols sometimes need to tell RA-originated IPv6 routes from other kernel routes to make proper routing decisions. This makes most sense for RA routes with nexthops, namely, default routes and Route Information routes. The intended mean of preserving RA route origin in a netlink message is through indicating RTPROT_RA as protocol code. Function rt6_fill_node() tried to do that for default routes, but its test condition was taken wrong. This change is modeled after the original mailing list posting by Jeff Haran. It fixes the test condition for default route case and sets the same behaviour for Route Information case (both types use nexthops). Handling of the 3rd RA route type, Prefix Information, is left unchanged, as it stands for interface connected routes (without nexthops). Signed-off-by: Denis Ovsienko <infrastation@yandex.ru> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Haiyang Zhang authored
This adds support for setting synthetic NIC MAC address from within Linux guests. Before using this feature, the option "spoofing of MAC address" should be enabled at the Hyper-V manager / Settings of the synthetic NIC. Thanks to Kin Cho <kcho@infoblox.com> for the initial implementation and tests. And, thanks to Long Li <longli@microsoft.com> for the debugging works. Reported-and-tested-by: Kin Cho <kcho@infoblox.com> Reported-by: Long Li <longli@microsoft.com> Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com> Reviewed-by: K. Y. Srinivasan <kys@microsoft.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Tony Cheneau authored
Lenght field should be encoded using big endian byte order, such as intend in the specs. As it is currently written, the len field would not be decoded properly on an implementation using the correct byte ordering. Hence, it could lead to interroperability issues. Also, I rewrote the code so that iphc0 argument of lowpan_alloc_new_frame could be removed. Signed-off-by: Tony Cheneau <tony.cheneau@amnesiak.org> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Tony Cheneau authored
The tag field should be stored and accessed using big endian byte order (as intended in the specs). Or else, when displayed with a trafic analyser, such a Wireshark, the field not properly displayed (e.g. 0x01 00 instead of 0x00 01, and so on). Signed-off-by: Tony Cheneau <tony.cheneau@amnesiak.org> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Tony Cheneau authored
When a UDP packet gets fragmented, a crash will occur at reassembly time. This is because skb->transport_header is not set during earlier period of fragment reassembly. As a consequence, call to udp_hdr() return NULL and uh (which is NULL) gets dereferenced without much test. Signed-off-by: Tony Cheneau <tony.cheneau@amnesiak.org> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Joe Perches authored
Convert the existing uses of random_ether_addr to the new eth_random_addr. Signed-off-by: Joe Perches <joe@perches.com> Acked-by: Mike Frysinger <vapier@gentoo.org> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Joe Perches authored
Convert the existing uses of random_ether_addr to the new eth_random_addr. Signed-off-by: Joe Perches <joe@perches.com> Acked-by: Felipe Balbi <balbi@ti.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Joe Perches authored
Convert the existing uses of random_ether_addr to the new eth_random_addr. Signed-off-by: Joe Perches <joe@perches.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Joe Perches authored
Convert the existing uses of random_ether_addr to the new eth_random_addr. Signed-off-by: Joe Perches <joe@perches.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Joe Perches authored
Convert the existing uses of random_ether_addr to the new eth_random_addr. Signed-off-by: Joe Perches <joe@perches.com> Acked-by: Hin-Tak Leung <htl10@users.sourceforge.net> Acked-by: Gertjan van Wingerde <gwingerde@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Joe Perches authored
Convert the existing uses of random_ether_addr to the new eth_random_addr. Signed-off-by: Joe Perches <joe@perches.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Joe Perches authored
Convert the existing uses of random_ether_addr to the new eth_random_addr. Signed-off-by: Joe Perches <joe@perches.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Joe Perches authored
Add some API symmetry to eth_broadcast_addr and add a #define to the old name for backward compatibility. Signed-off-by: Joe Perches <joe@perches.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
git://git.kernel.org/pub/scm/linux/kernel/git/paulg/linuxDavid S. Miller authored
Paul Gortmaker says: ==================== This is the same eight commits as sent for review last week[1], with just the incorporation of the pr_fmt change as suggested by JoeP. There was no additional change requests, so unless you can see something else you'd like me to change, please pull. ... Erik Hugne (5): tipc: use standard printk shortcut macros (pr_err etc.) tipc: remove TIPC packet debugging functions and macros tipc: simplify print buffer handling in tipc_printf tipc: phase out most of the struct print_buf usage tipc: remove print_buf and deprecated log buffer code Paul Gortmaker (3): tipc: factor stats struct out of the larger link struct tipc: limit error messages relating to memory leak to one line tipc: simplify link_print by divorcing it from using tipc_printf ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
-
Andrey Vagin authored
Before this patch sock_diag works for init_net only and dumps information about sockets from all namespaces. This patch expands sock_diag for all name-spaces. It creates a netlink kernel socket for each netns and filters data during dumping. v2: filter accoding with netns in all places remove an unused variable. Cc: "David S. Miller" <davem@davemloft.net> Cc: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> Cc: James Morris <jmorris@namei.org> Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org> Cc: Patrick McHardy <kaber@trash.net> Cc: Pavel Emelyanov <xemul@parallels.com> CC: Eric Dumazet <eric.dumazet@gmail.com> Cc: linux-kernel@vger.kernel.org Cc: netdev@vger.kernel.org Signed-off-by: Andrew Vagin <avagin@openvz.org> Acked-by: Pavel Emelyanov <xemul@parallels.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Duan Jiong authored
Remove duplicated #include <linux/delay.h> in drivers/net/ethernet/nxp/lpc_eth.c Signed-off-by: Duan Jiong<djduanjiong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Eric Dumazet authored
Add three SNMP TCP counters, to better track TCP behavior at global stage (netstat -s), when packets are received Out Of Order (OFO) TCPOFOQueue : Number of packets queued in OFO queue TCPOFODrop : Number of packets meant to be queued in OFO but dropped because socket rcvbuf limit hit. TCPOFOMerge : Number of packets in OFO that were merged with other packets. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
- 14 Jul, 2012 10 commits
-
-
Alexander Duyck authored
This change merges the ixgbe_cache_ring_fcoe and ixgbe_set_fcoe_queues logic into the DCB and RSS initialization calls. Cc: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com> Tested-by: Ross Brattain <ross.b.brattain@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
-
Alexander Duyck authored
In upcoming patches it will become increasingly common to need to determine the FCoE traffic class in order to determine the correct queues for FCoE. In order to make this easier I am adding a function for obtaining the FCoE traffic class based on the user priority. Cc: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com> Tested-by: Ross Brattain <ross.b.brattain@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
-
Alexander Duyck authored
There were cases where the prio_tc_map was not populated when we were calling open. This will result in us incorrectly configuring the traffic classes when DCB is enabled. In order to correct this I have updated the code so that we now populate the values prior to allocating the q_vectors and calling ixgbe_open. Cc: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com> Tested-by: Ross Brattain <ross.b.brattain@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
-
Alexander Duyck authored
This is meant to be a generic clean-up of the remaining functions for unpacking data from the DCB structures. The only real changes are: replaced the variable i with tc for functions that were looping through the traffic classes, and added a pointer for tc_class instead of path since that way we only need to pull the pointer once instead of once per loop. Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com> Tested-by: Ross Brattain <ross.b.brattain@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
-
Alexander Duyck authored
This patch is meant to help simplify the logic for getting traffic classes from user priorities. To do this I am adding a function named ixgbe_dcb_get_tc_from_up that will go through the traffic classes in reverse order in order to determine which traffic class contains a bit for a given user priority. Adding a declaration for this new function to the header so that we have a centralized means for sorting out traffic classes belonging to features such as FCoE. Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com> Tested-by: Ross Brattain <ross.b.brattain@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
-
Matthew Vick authored
When configuring interrupt throttling on 82574 in MSI-X mode, we need to be programming the EITR registers instead of the ITR register. -rc2: Renamed e1000_write_itr() to e1000e_write_itr(), fixed whitespace issues, and removed unnecessary !! operation. -rc3: Reduced the scope of the loop variable in e1000e_write_itr(). Signed-off-by: Matthew Vick <matthew.vick@intel.com> Acked-by: Bruce Allan <bruce.w.allan@intel.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
-
Tushar Dave authored
Cleanup code to make it more clean and readable. Signed-off-by: Tushar Dave <tushar.n.dave@intel.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
-
Steffen Klassert authored
We start initializing the struct xfrm_dst at the first field behind the struct dst_enty. This is error prone because it might leave a new field uninitialized. So start initializing the struct xfrm_dst right behind the dst_entry. Suggested-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
Steffen Klassert authored
We start initializing the struct rt6_info at the first field behind the struct dst_enty. This is error prone because it might leave a new field uninitialized. So start initializing the struct rt6_info right behind the dst_entry. Suggested-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-
git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-nextDavid S. Miller authored
John Linville says: ==================== Several drivers see updates: mwifiex, ath9k, iwlwifi, brcmsmac, wlcore/wl12xx/wl18xx, and a handful of others. The bcma bus got a lot of attention from Hauke Mehrtens. The cfg80211 component gets a flurry of patches for multi-channel support, and the mac80211 component gets the first few VHT (11ac) and 60GHz (11ad) patches. This also includes the removal of the iwmc3200 drivers, since the hardware never became available to normal people. Additionally, the NFC subsystem gets a series of updates. According to Samuel, "Here are the interesting bits: - A better error management for the HCI stack. - An LLCP "late" binding implementation for a better NFC SAP usage. SAPs are now reserved only when there's a client for it. - Support for Sony RC-S360 (a.k.a. PaSoRi) pn533 based dongle. We can read and write NFC tags and also establish a p2p link with this dongle now. - A few LLCP fixes." Finally, this includes another pull of the fixes from the wireless tree in order to resolve some merge issues. ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
-
- 13 Jul, 2012 5 commits
-
-
Erik Hugne authored
The internal log buffer handling functions can now safely be removed since there is no code using it anymore. Requests to interact with the internal tipc log buffer over netlink (in config.c) will report 'obsolete command'. This represents the final removal of any references to a struct print_buf, and the removal of the struct itself. We also get rid of a TIPC specific Kconfig in the process. Finally, log.h is removed since it is not needed anymore. Signed-off-by: Erik Hugne <erik.hugne@ericsson.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
-
Erik Hugne authored
The tipc_printf is renamed to tipc_snprintf, as the new name describes more what the function actually does. It is also changed to take a buffer and length parameter and return number of characters written to the buffer. All callers of this function that used to pass a print_buf are updated. Final removal of the struct print_buf itself will be done synchronously with the pending removal of the deprecated logging code that also was using it. Functions that build up a response message with a list of ports, nametable contents etc. are changed to return the number of characters written to the output buffer. This information was previously hidden in a field of the print_buf struct, and the number of chars written was fetched with a call to tipc_printbuf_validate. This function is removed since it is no longer referenced nor needed. A generic max size ULTRA_STRING_MAX_LEN is defined, named in keeping with the existing TIPC_TLV_ULTRA_STRING, and the various definitions in port, link and nametable code that largely duplicated this information are removed. This means that amount of link statistics that can be returned is now increased from 2k to 32k. The buffer overflow check is now done just before the reply message is passed over netlink or TIPC to a remote node and the message indicating a truncated buffer is changed to a less dramatic one (less CAPS), placed at the end of the message. Signed-off-by: Erik Hugne <erik.hugne@ericsson.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
-
Erik Hugne authored
tipc_printf was previously used both to construct debug traces and to append data to buffers that should be sent over netlink to the tipc-config application. A global print_buffer was used to format the string before it was copied to the actual output buffer. This could lead to concurrent access of the global print_buffer, which then had to be lock protected. This is simplified by changing tipc_printf to append data directly to the output buffer using vscnprintf. With the new implementation of tipc_printf, there is no longer any risk of concurrent access to the internal log buffer, so the lock (and the comments describing it) are no longer strictly necessary. However, there are still a few functions that do grab this lock before resizing/dumping the log buffer. We leave the lock, and these functions untouched since they will be removed with a subsequent commit that drops the deprecated log buffer handling code Signed-off-by: Erik Hugne <erik.hugne@ericsson.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
-
Paul Gortmaker authored
To pave the way for a pending cleanup of tipc_printf, and removal of struct print_buf entirely, we make that task simpler by converting link_print to issue its messages with standard printk infrastructure. [Original idea separated from a larger patch from Erik Hugne <erik.hugne@ericsson.com>] Cc: Erik Hugne <erik.hugne@ericsson.com> Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
-
Erik Hugne authored
The link queue traces and packet level debug functions served a purpose during early development, but are now redundant since there are other, more capable tools available for debugging at the packet level. The TIPC_DEBUG Kconfig option is removed since it does not provide any extra debugging features anymore. This gets rid of a lot of tipc_printf usages, which will make the pending cleanup work of that function easier. Signed-off-by: Erik Hugne <erik.hugne@ericsson.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
-